arXiv subjects

Kejiang Ye

Publications and source records attributed to Kejiang Ye.

At least 19 recordsLinked to original sources

arXiv2026

Movable-Antenna Assisted Energy Minimization in UAV-Enabled Mobile Edge Computing Systems

Driven by the exponential growth of latency-sensitive applications, mobile edge computing (MEC) has emerged as a pivotal paradigm, yet mitigating its substantial energy consumption remains critical. This paper explores a movable-antenna (MA) assisted energy minimization scheme in an uncrewed aerial vehicle (UAV)-enabled MEC system, where a UAV equipped with an MA array serves as an edge server to process tasks offloaded from terrestrial consumer electronics (CE) devices. To minimize the total system energy consumption, we jointly optimize computation resource allocation, CE transmit power, receive beamforming, and MA positions. To tackle the resulting non-convex problem with coupled variables, a robust alternating optimization algorithm based on the block coordinate descent method is developed. The problem is iteratively decomposed into three subproblems. In particular, the subproblem of transmit power and receive beamforming is reformulated and optimized using the quadratic transform technique, while the MA array positions are optimized via the particle swarm optimization algorithm. Numerical simulations verify that the proposed scheme achieves substantial energy savings over conventional benchmarks.

cs.IT↗

arXiv2026

BrownoutMoE: Structure-Aware Expert Grouping for Efficient and Accurate LLM Web-based Services

Mixture-of-Experts (MoE) large language models (LLMs) are increasingly deployed in Web-facing services, where inference must be both accurate and responsive under bursty demand. Although MoE models improve parameter efficiency through sparse expert activation, efficient MoE inference remains challenging in practice. A major reason is the highly imbalanced expert access pattern during inference: a few hot experts process most routed tokens, while many cold experts are rarely activated, leaving GPU parallelism underutilized. Existing systems mainly optimize runtime execution, such as scheduling, communication overlap, and kernel fusion, but usually preserve the original expert organization and therefore do not address the structural inefficiency caused by fragmented expert usage. In this paper, we present \textbf{BrownoutMoE}, a structure-aware optimization framework for efficient and accurate MoE inference services. Inspired by the brownout paradigm in service computing, BrownoutMoE reorganizes experts into groups to improve utilization and system efficiency while maintaining service quality. Specifically, we formulate layer-wise expert grouping as a learning problem and employ reinforcement learning to discover grouping strategies that minimize accuracy degradation. We further introduce a grouping-consistent distillation process to produce deployable models that are compatible with standard inference pipelines. Experimental results demonstrate that BrownoutMoE reduces accuracy degradation by up to 71.4% and improves throughput by up to 2.24x over baselines.

cs.DC↗

arXiv2026

CoCoScale: Leveraging Layer-wise Scaling to Unlock the Potential of Online LLM Serving

Online large language model (LLM) serving has become the backbone of modern AI applications, powering diverse downstream services through shared hardware clusters. However, modern serving systems frequently encounter highly dynamic workloads characterized by severe workload skewness, where a small fraction of model instances receives the vast majority of traffic. Existing instance-level scaling mechanisms are limited by coarse-grained resource adjustment: scaling up requires the cold-start of full-model replicas, incurring substantial latency, while scaling down leaves the system vulnerable to performance degradation during sudden traffic surges. The key insight of this work is that LLM serving offers a unique opportunity for fine-grained scaling. In this paper, we propose CoCoScale, a layer-wise dynamic scaling mechanism that selectively expands the parallelism of hot layers onto idle resources reclaimed from underutilized devices, enabling elastic data parallelism without altering model architectures or adding hardware overhead. Evaluations demonstrate that CoCoScale significantly reduces cold start latency by 97.9%-99.3% compared to traditional scale up. Under production traces, CoCoScale reduces average latency by 20.7\%--28.1\% and achieves full Service Level Objective (SLO) attainment, demonstrating superior dynamic adaptability and resource efficiency.

cs.DC↗

arXiv2026

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning

Large language model (LLM) post-training for reasoning increasingly relies on reinforcement learning with verifiable rewards (RLVR), where models learn from ground-truth feedback on mathematical, logical, and scientific tasks. To enable flexible resource allocation and support heterogeneous training setups, modern RLVR systems adopt disaggregated architectures that decouple rollout generation and policy training across independent GPU pools. However, existing synchronous on-policy GRPO (Group Relative Policy Optimization) RLVR systems finish an entire rollout before starting training, leaving the trainer GPU pool idle while rollout is still ongoing. Asynchronous RL pipelines overlap the two stages, but at the cost of training on stale data. To address these challenges, we propose RolloutPipe, a post-training framework for disaggregated RLVR systems, which turns the fixed-weight rollout into a complete-group pipeline where trainable groups move to the trainer while later groups are still being generated. RolloutPipe achieves this through two techniques including complete-group pipelining (CGP) and frontier-group dispatch (FGD). CGP dispatches each trainable complete group to the trainer FIFO as soon as group materialization finishes, and FGD is an admission policy on the Rollout node that first admits requests for the frontier groups needed to form the next training batch, so that trainer-ready groups arrive earlier and more steadily. The design starts training before the rollout completes while maintaining on-policy correctness. Evaluated on Qwen3-1.7B across four reasoning and science benchmarks and twelve rollout settings, RolloutPipe shortens the rollout-to-train-end time by 30.7%-42.3%, and lowers the trainer waiting ratio by 37%-76% compared to Slime, a state-of-the-art rollout and training system.

cs.DC↗

arXiv2026

SwiftCache: Efficient LLM Serving for Multi-turn Conversations with Heterogeneous KV Cache Sharing

Multi-turn conversation is a fundamental scenario in LLM applications, widely used in chatbots and AI agents. As the conversation evolves, historical tokens accumulate continuously. Existing systems cache their key-value (KV) pairs to avoid redundant computation. However, limited GPU memory (HBM) capacity often forces these KV caches to be offloaded to CPU memory or SSD, making KV cache reloads increasingly costly in terms of latency as the context grows. Meanwhile, the constrained HBM capacity also limits the maximum inference length, thereby restricting the number of turns that can be supported in a conversation. To address these two challenges, we propose SwiftCache, a collaborative inference system that enables heterogeneous models to share underutilized GPU memory and NVLink bandwidth within a server. Specifically, models with low KV cache demand donate idle GPU memory to store the prefix cache of high-demand models, allowing cross-model KV cache sharing over NVLink and avoiding slow PCIe transfers. SwiftCache further reduces memory pressure by keeping only the KV cache of the currently active layer in local GPU memory, thereby enabling longer-context inference. Our experiments on real-world workloads show that SwiftCache reduces P99 time-to-first-token (TTFT) by up to 69% and extends maximum context length by up to 3.98x compared to vLLM and SGLang, with minimal interference to co-located models.

cs.DC↗

arXiv2026

6DMA-Enabled ISAC for Low-Altitude Economy

In this paper, we investigate a six dimensional movable antenna (6DMA) enable integrated sensing and communications (ISAC) network in low-altitude economy. The studied 6DMA can move in a three-dimensional space and rotate around its surface center, making full use of spatial freedom to adapt to the different location distributions of uncrewed aerial vehicles (UAVs) adjust channel conditions in time. However, since the rotation and location change of 6DMA requires the assistance of a physical device, it is unreasonable for 6DMA to change locations too frequently. Therefore, we propose a hierarchical deep reinforcement learning algorithm based on twin delayed deep deterministic policy gradient. The first layer optimizes the rotation and location of 6DMA with infrequent updates, and the second layer optimizes the UAV flight direction and base station transmit beamforming matrix in each time slot. Under the condition of satisfying the sensing intensity of the sensing target, the total data transmission rate to the UAVs is maximized. The numerical results show that the proposed 6DMA-enable ISAC algorithm through joint optimization of multiple variables performs significantly better than the partially movable scheme and the fixed antenna position scheme.

eess.SP↗

arXiv2026

Memory Centric Power Allocation for Multi-Agent Embodied Question Answering

This paper considers multi-agent embodied question answering (MA-EQA), which enables robot teams to answer queries based on their long-horizon observations. In contrast to existing edge resource management methods that optimize sensing, communication, or computation performance metrics, MA-EQA focuses on the quality of aggregated memory. To address this paradigm shift, we propose a quality of memory (QoM) model based on generative adversarial exam (GAE), which leverages forward simulation to evaluate memory retrieval and utilizes the resulting exam scores to quantify QoM. Based on the QoM model, we develop a memory-centric power allocation (MCPA) scheme that maximizes memory quality under communication resource constraints. Through analytical characterization in the noise-limited regime, we reveal a GAE-augmented capped water-filling structure for MCPA. Extensive experiments demonstrate that MCPA achieves significant improvements over existing benchmarks across diverse metrics and scenarios.

cs.RO↗

arXiv2026

Cloud-native and Distributed Systems for Efficient and Scalable Large Language Models -- A Research Agenda

The rapid rise of Large Language Models (LLMs) has revolutionized various artificial intelligence (AI) applications, from natural language processing to code generation. However, the computational demands of these models, particularly in training and inference, present significant challenges. Traditional systems are often unable to meet these requirements, necessitating the integration of cloud-native and distributed architectures. This paper explores the role of cloud platforms and distributed systems in supporting the scalability, efficiency, and optimization of LLMs. We discuss the complexities of LLM deployment, including data management, resource optimization, and the need for microservices, autoscaling, and hybrid cloud-edge solutions. Additionally, we examine emerging research trends, such as serverless inference, quantum computing, and federated learning, and their potential to drive the next phase of LLM innovation. The paper concludes with a roadmap for future developments, emphasizing the need for continued research, standardization, and cross-sector collaboration to sustain the growth of LLMs in both research and enterprise applications.

cs.DC↗

arXiv2025

DOPD: A Dynamic PD-Disaggregation Architecture for Maximizing Goodput in LLM Inference Serving

To meet strict Service-Level Objectives (SLOs),contemporary Large Language Models (LLMs) decouple the prefill and decoding stages and place them on separate GPUs to mitigate the distinct bottlenecks inherent to each phase. However, the heterogeneity of LLM workloads causes producerconsumer imbalance between the two instance types in such disaggregated architecture. To address this problem, we propose DOPD (Dynamic Optimal Prefill/Decoding), a dynamic LLM inference system that adjusts instance allocations to achieve an optimal prefill-to-decoding (P/D) ratio based on real-time load monitoring. Combined with an appropriate request-scheduling policy, DOPD effectively resolves imbalances between prefill and decoding instances and mitigates resource allocation mismatches due to mixed-length requests under high concurrency. Experimental evaluations show that, compared with vLLM and DistServe (representative aggregation-based and disaggregationbased approaches), DOPD improves overall system goodput by up to 1.5X, decreases P90 time-to-first-token (TTFT) by up to 67.5%, and decreases P90 time-per-output-token (TPOT) by up to 22.8%. Furthermore, our dynamic P/D adjustment technique performs proactive reconfiguration based on historical load, achieving over 99% SLOs attainment while using less additional resources.

cs.DC↗

arXiv2025

Edge Collaborative Gaussian Splatting with Integrated Rendering and Communication

Gaussian splatting (GS) struggles with degraded rendering quality on low-cost devices. To address this issue, we present edge collaborative GS (ECO-GS), where each user can switch between a local small GS model to guarantee timeliness and a remote large GS model to guarantee fidelity. However, deciding how to engage the large GS model is nontrivial, due to the interdependency between rendering requirements and resource conditions. To this end, we propose integrated rendering and communication (IRAC), which jointly optimizes collaboration status (i.e., deciding whether to engage large GS) and edge power allocation (i.e., enabling remote rendering) under communication constraints across different users by minimizing a newly-derived GS switching function. Despite the nonconvexity of the problem, we propose an efficient penalty majorization minimization (PMM) algorithm to obtain the critical point solution. Furthermore, we develop an imitation learning optimization (ILO) algorithm, which reduces the computational time by over 100x compared to PMM. Experiments demonstrate the superiority of PMM and the real-time execution capability of ILO.

cs.IT↗

arXiv2025

BanaServe: Unified KV Cache and Dynamic Module Migration for Balancing Disaggregated LLM Serving in AI Infrastructure

Large language models (LLMs) are increasingly deployed in AI infrastructure, driving the need for high throughput, resource efficient serving systems. Disaggregated LLM serving, which separates prompt prefill from auto-regressive decode, has emerged as a promising architecture by isolating their heterogeneous compute and memory demands. However, current disaggregated systems face three key limitations: (i) static resource allocation cannot adapt to highly dynamic workloads, causing over-provisioning that wastes resources or under-provisioning that violates service level objectives (SLOs); (ii) inherent load imbalance between prefill and decode stages, where prefill is compute-bound and decode is memory-bound, causes under-utilization in one tier while the other becomes a bottleneck; and (iii) prefix cache aware routing skews load distribution, as high cache hit rate prefill nodes attract disproportionately more requests, further degrading balance and efficiency. To address these issues, we present BanaServe, a dynamic orchestration framework that continuously rebalances computational and memory resources across prefill and decode instances while eliminating hotspots induced by cache. BanaServe introduces layer level weight migration, attention level Key Value Cache (KV Cache) migration, and Global KV Cache Store sharing with layer wise overlapped transmission, enabling both coarse grained (layer level) and fine grained (attention level) load redistribution with minimal latency overhead. These mechanisms allow routers to perform purely load aware scheduling, unconstrained by cache placement. Compared to vLLM, BanaServe achieves 1.2x-3.9x higher throughput with 3.9%-78.4% lower total processing time, and outperforms DistServe by 1.1x-2.8x in throughput with 1.4%-70.1% latency reduction.

cs.DC↗

arXiv2025

FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters

Serving Large Language Models (LLMs) in production faces significant challenges from highly variable request patterns and severe resource fragmentation in serverless clusters. Current systems rely on static pipeline configurations that struggle to adapt to dynamic workload conditions, leading to substantial inefficiencies. We present FlexPipe, a novel system that dynamically reconfigures pipeline architectures during runtime to address these fundamental limitations. FlexPipe decomposes models into fine-grained stages and intelligently adjusts pipeline granularity based on real-time request pattern analysis, implementing three key innovations: fine-grained model partitioning with preserved computational graph constraints, inflight pipeline refactoring with consistent cache transitions, and topology-aware resource allocation that navigates GPU fragmentation. Comprehensive evaluation on an 82-GPU cluster demonstrates that FlexPipe achieves up to 8.5x better resource efficiency while maintaining 38.3% lower latency compared to state-of-the-art systems, reducing GPU reservation requirements from 75% to 30% of peak capacity.

cs.DC↗

arXiv2025

TD3-Sched: Learning to Orchestrate Container-based Cloud-Edge Resources via Distributed Reinforcement Learning

Resource scheduling in cloud-edge systems is challenging as edge nodes run latency-sensitive workloads under tight resource constraints, while existing centralized schedulers can suffer from performance bottlenecks and user experience degradation. To address the issues of distributed decisions in cloud-edge environments, we present TD3-Sched, a distributed reinforcement learning (DRL) scheduler based on Twin Delayed Deep Deterministic Policy Gradient (TD3) for continuous control of CPU and memory allocation, which can achieve optimized decisions for resource provisioning under dynamic workloads. On a realistic cloud-edge testbed with SockShop application and Alibaba traces, TD3-Sched achieves reductions of 17.9% to 38.6% in latency under same loads compared with other reinforcement-learning and rule-based baselines, and 16% to 31.6% under high loads. TD3-Sched also shows superior Service Level Objective (SLO) compliance with only 0.47% violations. These results indicate faster convergence, lower latency, and more stable performance while preserving service quality in container-based cloud-edge environment compared with the baselines.

cs.DC↗

arXiv2025

RSMA-Enhanced Data Collection in RIS-Assisted Intelligent Consumer Transportation Systems

This paper investigates the data collection enhancement problem in a reconfigurable intelligent surface (RIS)-empowered intelligent consumer transportation system (ICTS). We propose a novel framework where a data center (DC) provides energy to pre-configured roadside unit (RSU) pairs during the downlink stage. While in the uplink stage, these RSU pairs utilize a hybrid rate-splitting multiple access (RSMA) and time-division multiple access (TDMA) protocol to transmit the processed data to the DC, while simultaneously performing local data processing using the harvested energy. Our objective is to maximize the minimal processed data volume of the RSU pairs by jointly optimizing the RIS downlink and uplink phase shifts, the transmit power of the DC and RSUs, the RSU computation resource allocation, and the time slot allocation. To address the formulated non-convex problem, we develop an efficient iterative algorithm integrating alternating optimization and sequential rank-one constraint relaxation methods. Extensive simulations demonstrate that the proposed algorithm significantly outperforms baseline schemes under diverse scenarios, validating its effectiveness in enhancing the data processing performance for intelligent transportation applications.

cs.IT↗

arXiv2025

Joint Beamforming Design for RIS-Empowered NOMA-ISAC Systems

This paper investigates a reconfigurable intelligent surface (RIS)-assisted integrated sensing and communication (ISAC) system and proposes a joint communication and sensing beamforming design based on non-orthogonal multiple access (NOMA) technology. The system employs a dual-functional base station (DFBS) to simultaneously serve multiple users and sense multiple targets with the aid of RIS. To maximize the sum-rate of users, we jointly optimize the DFBS's active beamforming, the RIS's reflection coefficients, and the radar receive filters. The optimization is performed under constraints including the radar signal-to-noise ratio thresholds, the user signal-to-interference-plus-noise ratio requirements, the phase shifts of the RIS, the total transmit power, the receive filters, and the successive interference cancellation decoding order. To tackle the complex interdependencies and non-convex nature of the optimization problem, we introduce an effective iterative algorithm based on the alternating optimization framework. Simulation results demonstrate that the proposed algorithm outperforms baseline algorithms, highlighting its distinct advantages in the considered RIS-empowered NOMA-ISAC systems.

cs.IT↗

arXiv2025

Communication Efficient Robotic Mixed Reality with Gaussian Splatting Cross-Layer Optimization

Realizing low-cost communication in robotic mixed reality (RoboMR) systems presents a challenge, due to the necessity of uploading high-resolution images through wireless channels. This paper proposes Gaussian splatting (GS) RoboMR (GSMR), which enables the simulator to opportunistically render a photo-realistic view from the robot's pose by calling ``memory'' from a GS model, thus reducing the need for excessive image uploads. However, the GS model may involve discrepancies compared to the actual environments. To this end, a GS cross-layer optimization (GSCLO) framework is further proposed, which jointly optimizes content switching (i.e., deciding whether to upload image or not) and power allocation (i.e., adjusting to content profiles) across different frames by minimizing a newly derived GSMR loss function. The GSCLO problem is addressed by an accelerated penalty optimization (APO) algorithm that reduces computational complexity by over $10$x compared to traditional branch-and-bound and search algorithms. Moreover, variants of GSCLO are presented to achieve robust, low-power, and multi-robot GSMR. Extensive experiments demonstrate that the proposed GSMR paradigm and GSCLO method achieve significant improvements over existing benchmarks on both wheeled and legged robots in terms of diverse metrics in various scenarios. For the first time, it is found that RoboMR can be achieved with ultra-low communication costs, and mixture of data is useful for enhancing GS performance in dynamic scenarios.

cs.RO↗

arXiv2025

BridgeNet: A Unified Multimodal Framework for Bridging 2D and 3D Industrial Anomaly Detection

Industrial anomaly detection for 2D objects has gained significant attention and achieved progress in anomaly detection (AD) methods. However, identifying 3D depth anomalies using only 2D information is insufficient. Despite explicitly fusing depth information into RGB images or using point cloud backbone networks to extract depth features, both approaches struggle to adequately represent 3D information in multimodal scenarios due to the disparities among different modal information. Additionally, due to the scarcity of abnormal samples in industrial data, especially in multimodal scenarios, it is necessary to perform anomaly generation to simulate real-world abnormal samples. Therefore, we propose a novel unified multimodal anomaly detection framework to address these issues. Our contributions consist of 3 key aspects. (1) We extract visible depth information from 3D point cloud data simply and use 2D RGB images to represent appearance, which disentangles depth and appearance to support unified anomaly generation. (2) Benefiting from the flexible input representation, the proposed Multi-Scale Gaussian Anomaly Generator and Unified Texture Anomaly Generator can generate richer anomalies in RGB and depth. (3) All modules share parameters for both RGB and depth data, effectively bridging 2D and 3D anomaly detection. Subsequent modules can directly leverage features from both modalities without complex fusion. Experiments show our method outperforms state-of-the-art (SOTA) on MVTec-3D AD and Eyecandies datasets. Code available at: https://github.com/Xantastic/BridgeNet

cs.CV↗

arXiv2025

C-Koordinator: Interference-aware Management for Large-scale and Co-located Microservice Clusters

Microservices transform traditional monolithic applications into lightweight, loosely coupled application components and have been widely adopted in many enterprises. Cloud platform infrastructure providers enhance the resource utilization efficiency of microservices systems by co-locating different microservices. However, this approach also introduces resource competition and interference among microservices. Designing interference-aware strategies for large-scale, co-located microservice clusters is crucial for enhancing resource utilization and mitigating competition-induced interference. These challenges are further exacerbated by unreliable metrics, application diversity, and node heterogeneity. In this paper, we first analyze the characteristics of large-scale and co-located microservices clusters at Alibaba and further discuss why cycle per instruction (CPI) is adopted as a metric for interference measurement in large-scale production clusters, as well as how to achieve accurate prediction of CPI through multi-dimensional metrics. Based on CPI interference prediction and analysis, we also present the design of the C-Koordinator platform, an open-source solution utilized in Alibaba cluster, which incorporates co-location and interference mitigation strategies. The interference prediction models consistently achieve over 90.3% accuracy, enabling precise prediction and rapid mitigation of interference in operational environments. As a result, application latency is reduced and stabilized across all percentiles (P50, P90, P99) response time (RT), achieving improvements ranging from 16.7% to 36.1% under various system loads compared with state-of-the-art system. These results demonstrate the system's ability to maintain smooth application performance in co-located environments.

cs.DC↗